k
keynews.ai
keynews.ai
WorkThe story, in brief

Agent bio bug bounty call

OpenAI puts $25K on the table. Find the jailbreak in ChatGPT's agent mode.

Reporting by OpenAI Blog 1 min brief
Illustration of independent geometric mechanisms passing paper tasks along branching amber tracks.
AI agents and the coordination of work.AI illustration by KeyNews
The KeyNews take

Why it matters

OpenAI is crowdsourcing adversarial testing of its agentic systems before wider deployment, signaling both confidence in safety architecture and acknowledgment that internal testing alone is insufficient—a bellwether for how AI labs will approach agent safety governance.

The key facts

10 to know

  1. OpenAI launches Bio Bug Bounty program for ChatGPT agent safety testing

  2. Bounty cap: $25,000 per vulnerability

  3. Focus: Universal jailbreak prompts and agent-specific safety gaps

  4. Program targets researcher community for adversarial validation

  5. Timing: Mid-July 2025, suggesting agent deployment phase

  6. OpenAI launched Bio Bug Bounty program for ChatGPT agents

  7. Up to $25,000 reward per valid vulnerability

  8. Focus: universal jailbreak prompts and agent safety

  9. Open to external researchers

  10. Tests agent behavior under adversarial conditions

Go to the source

OpenAI Blogopenai.com

Publisher excerpt: OpenAI invites researchers to its Bio Bug Bounty. Test the ChatGPT agent’s safety with a universal jailbreak prompt and win up to $25,000.
Read original report
Back to today's editionMore work news

The wider picture

View all
Paper-cut illustration of an amber microchip with circuit paths extending into a row of data-center cabinets.
AI illustration by KeyNews
Work01

It’s Donald Trump Versus MAGA on Data Centers

Political fracture over data-center expansion reveals a disconnect between federal AI strategy and grassroots opposition—a workplace/policy story about who pays for the compute buildout and who resists it.

Wired AI
Illustration of two anonymous hands arranging task cards around an amber tool on a shared desk.
AI illustration by KeyNews
Work02

Daily AI usage in the U.S. has more than doubled in just six months

AI adoption has crossed from early-adopter to mainstream in the US workforce and daily life. This shift signals that practitioners can expect AI fluency to become a baseline job requirement, and employers need to rethink training, tooling, and team composition around an AI-native workforce.

The Decoder
Illustration of two anonymous hands arranging task cards around an amber tool on a shared desk.
AI illustration by KeyNews
Work03

Trump announces "AI Force" and plans for an "AI czar" as he pushes unchecked AI growth

Policy and regulatory direction matter to practitioners and enterprises. Trump's announced AI governance model—institutional elevation via a dedicated force, appointment of a czar, and explicit rejection of regulation—reshapes the operating environment for AI deployment, data-center buildout, and talent strategy over the next term.

The Decoder